Канал: neptune_ai

Navigating Machine Learning Pipelines With ZenML

Navigating Machine Learning Pipelines With ZenML

Building #ml #ai platform: in-house vs. cloud provider

Building #ml #ai platform: in-house vs. cloud provider

Building a documentation #chatbot with #rag (#llms #largelanguagemodels)

Building a documentation #chatbot with #rag (#llms #largelanguagemodels)

ZenML’s biggest challenge: integration testing (#mlops pipelines)

ZenML’s biggest challenge: integration testing (#mlops pipelines)

Vector Databases: Combining Keyword and Vector Search

Vector Databases: Combining Keyword and Vector Search

Standardizing and Automating ML Processes With ZenML

Standardizing and Automating ML Processes With ZenML

#productmanagement in #ml platform teams

#productmanagement in #ml platform teams

#retrieval augmented generation and #milvus

#retrieval augmented generation and #milvus

#vectordatabases in fraud detection

#vectordatabases in fraud detection

Improving Internal Documentation for ML platform Components

Improving Internal Documentation for ML platform Components

Vector Databases: Combining Filtering With Vector Search

Vector Databases: Combining Filtering With Vector Search

#internal #documentation for #ml platform

#internal #documentation for #ml platform

Tradicional #vectordatabases use cases

Tradicional #vectordatabases use cases

The future of #llm evaluation (#ai engineer world's fair 2024)

The future of #llm evaluation (#ai engineer world's fair 2024)

Balancing Product Management and Engineering in ML/AI Platform Teams

Balancing Product Management and Engineering in ML/AI Platform Teams

When to Implement a Vector Database

When to Implement a Vector Database

Challenges in the #llm space (#ai engineer world's fair 2024)

Challenges in the #llm space (#ai engineer world's fair 2024)

Challenges in the #rag #llm space (#ai engineer world's fair)

Challenges in the #rag #llm space (#ai engineer world's fair)

Challenges in #genai (#ai engineer world's fair 2024)

Challenges in #genai (#ai engineer world's fair 2024)

Real-World Big Data Models

Real-World Big Data Models

The Story Behind ZenML: MLOps Framework for ML Pipelines

The Story Behind ZenML: MLOps Framework for ML Pipelines

Unsolved challenges in #genai (#ai engineer world's fair 2024)

Unsolved challenges in #genai (#ai engineer world's fair 2024)

#llm challenges (#ai engineer world's fair 2024)

#llm challenges (#ai engineer world's fair 2024)

What's next for #llms (#ai engineer world's fair 2024)

What's next for #llms (#ai engineer world's fair 2024)

GPU Acceleration in Vector Databases

GPU Acceleration in Vector Databases

Centralized vs. Decentralized ML Platform Team Structure

Centralized vs. Decentralized ML Platform Team Structure

Predictions for #llms (#ai engineer world's fair 2024)

Predictions for #llms (#ai engineer world's fair 2024)

Challenges and opportunities for #llms (#ai engineer world's fair)

Challenges and opportunities for #llms (#ai engineer world's fair)

Building a Documentation Chatbot With a Vector Database

Building a Documentation Chatbot With a Vector Database

#llm deployment space challenges (#ai engineer world's fair)

#llm deployment space challenges (#ai engineer world's fair)

Why DoorDash Built Its ML Prediction Platform

Why DoorDash Built Its ML Prediction Platform

ICML Research Paper With Ankit Gupta

ICML Research Paper With Ankit Gupta

ICML Research Paper With Claudio Miceli de Farias

ICML Research Paper With Claudio Miceli de Farias

ICML Research Paper With Zhi Zhou

ICML Research Paper With Zhi Zhou

#largelanguagemodels future bets (#ai engineer world's fair)

#largelanguagemodels future bets (#ai engineer world's fair)

ICML Research Paper With Setareh Rezaee

ICML Research Paper With Setareh Rezaee

ICML Research Paper With Gaurav Gupta

ICML Research Paper With Gaurav Gupta

Challenges in the #llm space (#ai engineer world's fair 2024)

Challenges in the #llm space (#ai engineer world's fair 2024)

ICML Research Paper With Shikha Surana

ICML Research Paper With Shikha Surana

ICML 2024: 100 Second Research Challenge With Yongchang Hao

ICML 2024: 100 Second Research Challenge With Yongchang Hao

ICML 2024: 100 Second Research Challenge With Yash Patel

ICML 2024: 100 Second Research Challenge With Yash Patel

Challenges in the #rag based systems (#ai engineer world's fair)

Challenges in the #rag based systems (#ai engineer world's fair)

ICML 2024: 100 Second Research Challenge With Som Sagar

ICML 2024: 100 Second Research Challenge With Som Sagar

ICML 2024: 100 Second Research Challenge With Mukesh Ghimire

ICML 2024: 100 Second Research Challenge With Mukesh Ghimire

ICML 2024: 100 Second Research Challenge With Theo Vincent

ICML 2024: 100 Second Research Challenge With Theo Vincent

ICML 2024: 100 Second Research Challenge With Evgeniia Tokarchuk

ICML 2024: 100 Second Research Challenge With Evgeniia Tokarchuk

ICML 2024: 100 Second Research Challenge With Jan Gerken

ICML 2024: 100 Second Research Challenge With Jan Gerken

ICML 2024: 100 Second Research Challenge With Xingyue Huang

ICML 2024: 100 Second Research Challenge With Xingyue Huang

Unsolved challenges in the #llm space (#ai engineer world's fair)

Unsolved challenges in the #llm space (#ai engineer world's fair)

ICML 2024: 100 Second Research Challenge With Jaron Maene

ICML 2024: 100 Second Research Challenge With Jaron Maene

ICML 2024: 100 Second Research Challenge With Kyoungseok Jang

ICML 2024: 100 Second Research Challenge With Kyoungseok Jang

The future of #largelanguagemodels (#ai engineer world's fair)

The future of #largelanguagemodels (#ai engineer world's fair)

ICML 2024: 100 Second Research Challenge With Novin Shahroudi

ICML 2024: 100 Second Research Challenge With Novin Shahroudi

ICML 2024: 100 Second Research Challenge With Indra Priyadarsini

ICML 2024: 100 Second Research Challenge With Indra Priyadarsini

#genai use cases at AXA (#ai engineer world's fair 2024)

#genai use cases at AXA (#ai engineer world's fair 2024)

ICML 2024: 100 Second Research Challenge With Ruben Ohana

ICML 2024: 100 Second Research Challenge With Ruben Ohana

ICML 2024: 100 Second Research Challenge With Soumya Shaw

ICML 2024: 100 Second Research Challenge With Soumya Shaw

Unsolved challenges in #generativeai (#ai engineer world's fair)

Unsolved challenges in #generativeai (#ai engineer world's fair)

ICML 2024: 100 Second Research Challenge With Olatunji Emmanuel

ICML 2024: 100 Second Research Challenge With Olatunji Emmanuel

Future bets for #llms (#ai engineer world's fair 2024)

Future bets for #llms (#ai engineer world's fair 2024)

ICML 2024: 100 Second Research Challenge With Victor Agostinelli

ICML 2024: 100 Second Research Challenge With Victor Agostinelli

Vector Databases: Segmentation and Maintenance

Vector Databases: Segmentation and Maintenance

#llm challenges for compliance (#ai engineer world's fair 2024)

#llm challenges for compliance (#ai engineer world's fair 2024)

Building ML Platforms for Enterprise Scale

Building ML Platforms for Enterprise Scale

#llm predictions (#ai engineer world's fair 2024)

#llm predictions (#ai engineer world's fair 2024)

Challenges in #generativeai (#ai engineer world's fair 2024)

Challenges in #generativeai (#ai engineer world's fair 2024)

AI Engineer World's Fair 2024: Interview Series

AI Engineer World's Fair 2024: Interview Series

#speechtotext and #texttospeech challenges (#ai engineer world's fair)

#speechtotext and #texttospeech challenges (#ai engineer world's fair)

The Future of LLM Evaluation With Sam Siye Yu (Trueface.ai)

The Future of LLM Evaluation With Sam Siye Yu (Trueface.ai)

Insights Into Unsolved GenAI Challenges With YK Sugi (Sourcegraph)

Insights Into Unsolved GenAI Challenges With YK Sugi (Sourcegraph)

#rag based model evolution at Cohere (#ai engineer world's fair)

#rag based model evolution at Cohere (#ai engineer world's fair)

Current LLM Challenges and Future Predictions With Phil Salesses (Move AI)

Current LLM Challenges and Future Predictions With Phil Salesses (Move AI)

Problems Solved at OpenPipe and LLM Bets With Kyle Corbitt

Problems Solved at OpenPipe and LLM Bets With Kyle Corbitt

LLM Deployment and Challenges in the Space With Pedro Torruella (OctoAI)

LLM Deployment and Challenges in the Space With Pedro Torruella (OctoAI)

#kubernetes distributions for #ml

#kubernetes distributions for #ml

GenAI Challenge: Open-Source vs. Closed-Source Models With Philip Kiely (Baseten)

GenAI Challenge: Open-Source vs. Closed-Source Models With Philip Kiely (Baseten)

GenAI Use Cases and Common Challenges With Jeronim Morina (AXA)

GenAI Use Cases and Common Challenges With Jeronim Morina (AXA)

The intersection of #neuroscience and #llms

The intersection of #neuroscience and #llms

RAG-Based LLM Challenges With Alison Cossette (Neo4j)

RAG-Based LLM Challenges With Alison Cossette (Neo4j)

HNSW for vector search (#vectordatabases #mlops)

HNSW for vector search (#vectordatabases #mlops)

Navigating GenAI: Raymond Thai on Challenges and Future Bets

Navigating GenAI: Raymond Thai on Challenges and Future Bets

Solutions-Driven AI and Challenges Ahead With Sam Julien (Writer)

Solutions-Driven AI and Challenges Ahead With Sam Julien (Writer)

#llms and potential #ml platform use cases

#llms and potential #ml platform use cases

LLM Challenges For Compliance With Arun Prasad (AI Whispr)

LLM Challenges For Compliance With Arun Prasad (AI Whispr)

Challenges in the LLM Space With Francisco Ingham (Pampa Labs)

Challenges in the LLM Space With Francisco Ingham (Pampa Labs)

Challenges in Generative AI With David Li (Etsy)

Challenges in Generative AI With David Li (Etsy)

Indexing strategies for #vectordatabases

Indexing strategies for #vectordatabases

Observability in LLMOps: Different Levels of Scale With Aurimas Griciūnas

Observability in LLMOps: Different Levels of Scale With Aurimas Griciūnas

ZenML and #llm security (#mlops world 2023)

ZenML and #llm security (#mlops world 2023)

The Evolution of the RAG-Based Models With Sandra Kublik (Cohere)

The Evolution of the RAG-Based Models With Sandra Kublik (Cohere)

Optimizing Vector Databases With Indexing Strategies

Optimizing Vector Databases With Indexing Strategies

Problems Solved at Deepgram and Challenges in the Speech-to-Text Space

Problems Solved at Deepgram and Challenges in the Speech-to-Text Space

Best practices for evaluating #llms with #ai Makerspace

Best practices for evaluating #llms with #ai Makerspace

ZenML’s Artifact Store vs. Experiment Tracker

ZenML’s Artifact Store vs. Experiment Tracker

Hosting and #finetuning #llms (#mlops #genai world)

Hosting and #finetuning #llms (#mlops #genai world)

#vectordatabases explained with Frank Liu

#vectordatabases explained with Frank Liu

Working with #bigdata: 14 years ago vs. now

Working with #bigdata: 14 years ago vs. now

Big Data Evolution: 14 Years Ago vs. Now

Big Data Evolution: 14 Years Ago vs. Now

Understanding ZenML (#mlops #ml pipelines)

Understanding ZenML (#mlops #ml pipelines)

The Basics of Vector Databases With Frank Liu

The Basics of Vector Databases With Frank Liu

Product Update June '24: Redesigned Navigation, Run Groups, Reports, and More

Product Update June '24: Redesigned Navigation, Run Groups, Reports, and More

#llm latency with Rajiv Shah (ML Engineer at #huggingface)

#llm latency with Rajiv Shah (ML Engineer at #huggingface)

When to add a #vectordatabase to your #mlops stack

When to add a #vectordatabase to your #mlops stack

Navigating Vector Databases: Indexing Strategies, GPU, and More

Navigating Vector Databases: Indexing Strategies, GPU, and More

The experiment tracker for foundation model training – neptune.ai

The experiment tracker for foundation model training – neptune.ai

#llm strategy at #doordash

#llm strategy at #doordash

Integrating Specialized Vertical ML Tools With ZenML

Integrating Specialized Vertical ML Tools With ZenML

The relation between #mlops, #devops and #llmops

The relation between #mlops, #devops and #llmops

Evaluation in #finetuning and #promptengineering

Evaluation in #finetuning and #promptengineering

DoorDash's Approach to Large Language Models

DoorDash's Approach to Large Language Models

ZenML’s artifact store vs. experiment tracker (#mlops #ml)

ZenML’s artifact store vs. experiment tracker (#mlops #ml)

From DevOps to MLOps to LLMOps

From DevOps to MLOps to LLMOps

#llm projects: data availability and maturity in enterprises

#llm projects: data availability and maturity in enterprises

#llms used at Digits with Hennes Hapke at #mlops world 2023

#llms used at Digits with Hennes Hapke at #mlops world 2023

Learnings From Building the ML Platform at DoorDash

Learnings From Building the ML Platform at DoorDash

Using #llms as evaluators

Using #llms as evaluators

From Open-Source to Cloud: The Future of ZenML

From Open-Source to Cloud: The Future of ZenML

The reality of building #ml platforms with Mikiko Bazeley

The reality of building #ml platforms with Mikiko Bazeley

Challenges of classical #llms with Rajiv Shah (ML Engineer at #huggingface)

Challenges of classical #llms with Rajiv Shah (ML Engineer at #huggingface)

Jobs-to-be-done in MLOps for LLMs With ZenML

Jobs-to-be-done in MLOps for LLMs With ZenML

Modular philosophy of #ubuntu with Maciej Mazur: MLOps World 2023

Modular philosophy of #ubuntu with Maciej Mazur: MLOps World 2023

HRS Group's Multi-Cloud Strategy

HRS Group's Multi-Cloud Strategy

ZenML applications in #llmops

ZenML applications in #llmops

Safeguarding #llms with Shreya Rajpal from Guardrails AI

Safeguarding #llms with Shreya Rajpal from Guardrails AI

Breaking Down Workflow Orchestration and Pipeline Authoring in MLOps

Breaking Down Workflow Orchestration and Pipeline Authoring in MLOps

The future of #mlops with #llms

The future of #mlops with #llms

Foundational Models Era | The Role of Data Scientist and ML Engineer

Foundational Models Era | The Role of Data Scientist and ML Engineer

Bringing #llms in-house with Adam Probst

Bringing #llms in-house with Adam Probst

#llm evaluation methods: models vs. humans

#llm evaluation methods: models vs. humans

Building ML Platform at Scout 24 [With Olalekan Elesin]

Building ML Platform at Scout 24 [With Olalekan Elesin]

Main challenges of the #ml training pipeline at Pinterest

Main challenges of the #ml training pipeline at Pinterest

Real-time Machine Learning | Mike Del Balso

Real-time Machine Learning | Mike Del Balso

#llms and feature stores with Mike Del Balso

#llms and feature stores with Mike Del Balso

Reviving and improving Kubeflow: #mlops world 2023

Reviving and improving Kubeflow: #mlops world 2023

Going Deep On Model Serving, Deploying LLMs and Anything Production-Deployment

Going Deep On Model Serving, Deploying LLMs and Anything Production-Deployment

#llm deployment considerations: #gpu vs. #cpu

#llm deployment considerations: #gpu vs. #cpu

End-to-end Platforms vs. Point Solutions [With Olalekan Elesin]

End-to-end Platforms vs. Point Solutions [With Olalekan Elesin]

Challenges with #llms

Challenges with #llms

Building #ml platform: lessons learned

Building #ml platform: lessons learned

Michelangelo's Feature Platform [With Co-Creator, Mike Del Balso]

Michelangelo's Feature Platform [With Co-Creator, Mike Del Balso]

Importance of long-term memory in #agentsystems

Importance of long-term memory in #agentsystems

Using LLMs to Drive Product Vision [With Olalekan Elesin]

Using LLMs to Drive Product Vision [With Olalekan Elesin]

Future applications of #llms

Future applications of #llms

What is neptune.ai? – Product demo

What is neptune.ai? – Product demo

The motivation behind internal #ml platforms

The motivation behind internal #ml platforms

Building the ML Platform at Scout24 | How to Ship Features People Actually Need

Building the ML Platform at Scout24 | How to Ship Features People Actually Need

Future plans for Canonical’s #ai #ml projects with Maciej Mazur (Principal ML Engineer)

Future plans for Canonical’s #ai #ml projects with Maciej Mazur (Principal ML Engineer)

Vector Databases and Feature Platforms [With Mike Del Balso From Tecton]

Vector Databases and Feature Platforms [With Mike Del Balso From Tecton]

#llm cost considerations: self-hosting vs. proprietary API

#llm cost considerations: self-hosting vs. proprietary API

#llm evaluation challenges with Greg Loughnane (#mlops world 2023)

#llm evaluation challenges with Greg Loughnane (#mlops world 2023)

The future of MLOps with LLMs | Mike Del Balso

The future of MLOps with LLMs | Mike Del Balso

Methods for evaluating #llms with Hennes Hapke

Methods for evaluating #llms with Hennes Hapke

The Story Behind Michelangelo | ML Platform at Uber

The Story Behind Michelangelo | ML Platform at Uber

Selecting the first #ml platform projects

Selecting the first #ml platform projects

How is DAGWorks different from its competitors? #mlops

How is DAGWorks different from its competitors? #mlops

Learnings From Building the ML Platform at Uber (Michelangelo)

Learnings From Building the ML Platform at Uber (Michelangelo)

How to Control Access to ML Models in Neptune?

How to Control Access to ML Models in Neptune?

Predictions for #llms with Charles Frye (#mlops #generativeai world 2023)

Predictions for #llms with Charles Frye (#mlops #generativeai world 2023)

The Crucial Role of Program Managers [ML Platform Team at Stitch Fix]

The Crucial Role of Program Managers [ML Platform Team at Stitch Fix]

Project success metrics at #gitlab

Project success metrics at #gitlab

The future of #opensource with Rajiv Shah (ML Engineer at #huggingface)

The future of #opensource with Rajiv Shah (ML Engineer at #huggingface)

Getting closer to the business as an #mlops engineer

Getting closer to the business as an #mlops engineer

Create and Save Custom Table Views in Neptune

Create and Save Custom Table Views in Neptune

Experiment tracking and LLMs

Experiment tracking and LLMs

End-to-end ML Platform Team Structure at Stitch Fix

End-to-end ML Platform Team Structure at Stitch Fix

What’s next for #llms with Greg Loughnane

What’s next for #llms with Greg Loughnane

#llmops vs. #mlops

#llmops vs. #mlops

Intersection of Neuroscience and LLMs, Agent Systems, and LLM Predictions

Intersection of Neuroscience and LLMs, Agent Systems, and LLM Predictions

How to Version and Compare Datasets in Neptune

How to Version and Compare Datasets in Neptune

Tips for working with #llms

Tips for working with #llms

Why Go Open-Source? The Insight Story of Hamilton at Stitch Fix

Why Go Open-Source? The Insight Story of Hamilton at Stitch Fix

Evaluating #llm models with Rajiv Shah (#mlops world 2023)

Evaluating #llm models with Rajiv Shah (#mlops world 2023)

User experience of plugging-in #guardrails #ai when using #chatgpt

User experience of plugging-in #guardrails #ai when using #chatgpt

Mastering LLMs with AI Makerspace: MLOps World 2023

Mastering LLMs with AI Makerspace: MLOps World 2023

Challenges when building #guardrails #ai: Shreya Rajpal at #mlops world 2023

Challenges when building #guardrails #ai: Shreya Rajpal at #mlops world 2023

ML Pipeline Management Using Open-Source: DAGWorks and Hamilton

ML Pipeline Management Using Open-Source: DAGWorks and Hamilton

Classical #ml models vs. #llms at Digits

Classical #ml models vs. #llms at Digits

Moving from #tensorflow to #pytorch

Moving from #tensorflow to #pytorch

Safeguarding LLMs with Guardrails AI: Shreya Rajpal at MLOps World 2023

Safeguarding LLMs with Guardrails AI: Shreya Rajpal at MLOps World 2023

How to Compare Experiments in Neptune

How to Compare Experiments in Neptune

Challenges of adopting #llms in production on your own infra

Challenges of adopting #llms in production on your own infra

#llm based evaluation

#llm based evaluation

The future of #opensource, #mlops and #llms

The future of #opensource, #mlops and #llms

LLM Evaluation, Cost Considerations, and the Future of Open-Source: Rajiv Shah at MLOps World 2023

LLM Evaluation, Cost Considerations, and the Future of Open-Source: Rajiv Shah at MLOps World 2023

#generativeai use cases at Digits

#generativeai use cases at Digits

Multi-task learning in #ml

Multi-task learning in #ml

The future of #kubernetes

The future of #kubernetes

ZenML in the #llm space with Adam Probst at #mlops World 2023

ZenML in the #llm space with Adam Probst at #mlops World 2023

MLOps World 2023: Interview Series with Aurimas Griciūnas

MLOps World 2023: Interview Series with Aurimas Griciūnas

How #mlops started at Pinterest

How #mlops started at Pinterest

Canonical | Ubuntu: The Future of Kubernetes and Open Source

Canonical | Ubuntu: The Future of Kubernetes and Open Source

GenAI and LLMs at Digits: Cost of Hosting, Fine-Tuning, Evaluation

GenAI and LLMs at Digits: Cost of Hosting, Fine-Tuning, Evaluation

MLOps at Pinterest with Aayush Mudgal: MLOps World 2023

MLOps at Pinterest with Aayush Mudgal: MLOps World 2023

ZenML in the LLM Space: Adam Probst at MLOps World 2023

ZenML in the LLM Space: Adam Probst at MLOps World 2023

How to Use Custom Dashboards in Neptune

How to Use Custom Dashboards in Neptune

How to Track ML Model Training: PyTorch + neptune.ai Integration

How to Track ML Model Training: PyTorch + neptune.ai Integration

How to Track Hyperparameters: Optuna + neptune.ai Integration

How to Track Hyperparameters: Optuna + neptune.ai Integration

How to Use Neptune for A/B Testing ML Models

How to Use Neptune for A/B Testing ML Models

Overview of Neptune's Architecture

Overview of Neptune's Architecture

How to Integrate Neptune Into Your Code

How to Integrate Neptune Into Your Code